© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 43217
    Prev
    Next
    INDEX
    Explanations

    the role of

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron activates on occurrences of the word “role” (or its plural “roles”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    祧
    -2.59
    橚
    -2.11
    ዡ
    -1.92
    嵛
    -1.87
     decorados
    -1.85
    觏
    -1.83
     Bedürfn
    -1.82
    稣
    -1.80
     gewöhnlich
    -1.77
    緜
    -1.74
    POSITIVE LOGITS
    on
    2.20
    en
    2.11
    ');
    2.05
    Y
    1.99
    W
    1.96
    9
    1.91
    经常
    1.86
    8
    1.85
    7
    1.83
    J
    1.83
    Activations Density 0.056%

    No Known Activations